Training in progress, epoch 2

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686fef64a02fcd9ed2e45d039710a9a9f082d3926dced4c99dc690869a8e0537
+oid sha256:390a1376b55d0a5cdb115d69efa353749e7692da857a69abd0246f3d656cf9af
 size 274758317

train_factual_consistency.ipynb

@@ -129,23 +129,14 @@
    "id": "6bc83d4c-378c-4313-b641-8ead0c02f715",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:XRT configuration not detected. Defaulting to preview PJRT runtime. To silence this warning and continue using PJRT, explicitly set PJRT_DEVICE to a supported device or configure XRT. To disable default device selection, set PJRT_SELECT_DEFAULT_DEVICE=0\n",
-      "WARNING:root:For more information about the status of PJRT, see https://github.com/pytorch/xla/blob/master/docs/pjrt.md\n",
-      "WARNING:root:Defaulting to PJRT_DEVICE=CPU\n"
-     ]
-    },
     {
      "data": {
       "text/html": [
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='2449' max='9180' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [2449/9180 15:00 < 41:17, 2.72 it/s, Epoch 8/30]\n",
+       "      <progress value='613' max='918' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [613/918 03:40 < 01:50, 2.77 it/s, Epoch 2/3]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -160,51 +151,15 @@
        "    <tr>\n",
        "      <td>1</td>\n",
        "      <td>No log</td>\n",
-       "      <td>0.292851</td>\n",
-       "      <td>0.890625</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>2</td>\n",
-       "      <td>0.417800</td>\n",
-       "      <td>0.252162</td>\n",
-       "      <td>0.890625</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>3</td>\n",
-       "      <td>0.417800</td>\n",
-       "      <td>0.206412</td>\n",
-       "      <td>0.912109</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>4</td>\n",
-       "      <td>0.189500</td>\n",
-       "      <td>0.255287</td>\n",
-       "      <td>0.906250</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>5</td>\n",
-       "      <td>0.113500</td>\n",
-       "      <td>0.273709</td>\n",
-       "      <td>0.912109</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>6</td>\n",
-       "      <td>0.113500</td>\n",
-       "      <td>0.319531</td>\n",
-       "      <td>0.904297</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>7</td>\n",
-       "      <td>0.068500</td>\n",
-       "      <td>0.381726</td>\n",
-       "      <td>0.896484</td>\n",
+       "      <td>0.283724</td>\n",
+       "      <td>0.869141</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table><p>\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='59' max='64' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [59/64 00:05 < 00:00, 10.02 it/s]\n",
+       "      <progress value='48' max='64' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [48/64 00:05 < 00:01, 9.12 it/s]\n",
        "    </div>\n",
        "    "
       ],
@@ -225,7 +180,7 @@
     "    learning_rate=1e-4,\n",
     "    per_device_train_batch_size=64,\n",
     "    per_device_eval_batch_size=8,\n",
-    "    num_train_epochs=30,\n",
+    "    num_train_epochs=3,\n",
     "    weight_decay=0.02,\n",
     "    evaluation_strategy=\"epoch\",\n",
     "    eval_accumulation_steps=4,\n",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a8fea2d112223bb5fc50f0e3b8457dcd3eefa65312f57e80712e85717a5f1f
+oid sha256:f5d46324e9f1183ab9f5cd775916c015c2346d0e87006d76736ec786cf5a5ccd
 size 4155